paper-with-me

Papers

Visual Explanations for Convolutional Neural Networks via Latent Traversal of Generative Adversarial Networks

2021-10-29 · Amil Dravid, Aggelos K. Katsaggelos

Lack of explainability in artificial intelligence, specifically deep neural networks, remains a bottleneck for implementing models in practice. Popular techniques such as Gradient-weighted Class Activation Mapping (Grad-CAM) provide a coarse map of salient features in an image, which rarely tells the whole story of what a convolutional neural network (CNN) learned. Using COVID-19 chest X-rays, we present a method for interpreting what a CNN has learned by utilizing Generative Adversarial Networks (GANs). Our GAN framework disentangles lung structure from COVID-19 features. Using this GAN, we can visualize the transition of a pair of COVID negative lungs in a chest radiograph to a COVID positive pair by interpolating in the latent space of the GAN, which provides fine-grained visualization of how the CNN responds to varying features within the lungs.

📄 PDF Abstract BibTeX arXiv:2111.00116

Code (1)

avdravid/LatentTraversalViz 공식 구현

Similar Papers 제목 키워드 기반

Counterfactual Explanations via Riemannian Latent Space Traversal

2024-11-04 · Paraskevas Pegios, Aasa Feragen, Andreas Abildtrup Hansen, Georgios Arvanitidis

The adoption of increasingly complex deep models has fueled an urgent need for insight into how these models make predictions. Counterfactual explanations form a powerful tool for providing actionable explanations to pra…

counterfactualCounterfactual ExplanationDecoder

ChemoVerse: Manifold traversal of latent spaces for novel molecule discovery

2020-09-29 · Harshdeep Singh, Nicholas McCarthy, Qurrat Ul Ain, Jeremiah Hayes

In order to design a more potent and effective chemical entity, it is essential to identify molecular structures with the desired chemical properties. Recent advances in generative models using neural networks and machin…

Heuristic Search

Towards Visually Explaining Variational Autoencoders

2019-11-18 · CVPR 2020 6 · Wenqian Liu, Runze Li, Meng Zheng, Srikrishna Karanam 외

Recent advances in Convolutional Neural Network (CNN) model interpretability have led to impressive progress in visualizing and understanding model predictions. In particular, gradient-based visual attention methods have…

Disentanglement

QUCE: The Minimisation and Quantification of Path-Based Uncertainty for Generative Counterfactual Explanations

2024-02-27 · Jamie Duell, Monika Seisenberger, Hsuan Fu, Xiuyi Fan

Deep Neural Networks (DNNs) stand out as one of the most prominent approaches within the Machine Learning (ML) domain. The efficacy of DNNs has surged alongside recent increases in computational capacity, allowing these …

counterfactualExplainable Models

Interpretable ECG classification via a query-based latent space traversal (qLST)

2021-11-14 · Melle B. Vessies, Sharvaree P. Vadgama, Rutger R. van de Leur, Pieter A. Doevendans 외

Electrocardiography (ECG) is an effective and non-invasive diagnostic tool that measures the electrical activity of the heart. Interpretation of ECG signals to detect various abnormalities is a challenging task that requ…

DiagnosticECG ClassificationElectrocardiography (ECG)